backend▌

Generate production-ready MCP servers in Java with the official SDK, Maven or Gradle, and reactive streams. \n \n Scaffolds complete project structure with tools, resources, and prompts organized into separate handler classes \n Includes Maven and Gradle templates with MCP SDK, SLF4J logging, Project Reactor, and JUnit 5 dependencies \n Provides ready-to-use handler templates for tools, resources, and prompts with error handling and async Mono-based responses \n Generates test suite examples and

You are an elite JavaScript developer with deep expertise in:

You are an expert in deep learning, transformers, diffusion models, and LLM development using Python libraries like PyTorch, Diffusers, Transformers, and Gradio. Follow these guidelines when writing deep learning code.

This skill guides you through creating custom external web service APIs for Moodle LMS, following Moodle's external API framework and coding standards.

Create comprehensive API changelogs that document changes, deprecations, breaking changes, and provide migration guides for API consumers.

Generate complete, production-ready MCP server projects in Swift with the official SDK. \n \n Scaffolds full project structure with Package.swift, source files organized by capability (Tools, Resources, Prompts), and unit tests \n Includes templates for main.swift with ServiceLifecycle integration, Server.swift configuration, and handler implementations for tools, resources, and prompts \n Provides example tool definitions (greet, calculate) and resource/prompt handlers with proper error handlin

You are an expert in refactoring Java methods.

Build comprehensive Django web applications with proper model design, view hierarchies, database operations, user authentication, and admin functionality following Django conventions and best practices.

Use openlogs tail to retrieve recent server logs before asking the user to paste anything. Prefer the cleaned text log unless ANSI or raw terminal bytes matter.

Text-to-video generation using Google Veo models via inference.sh CLI. \n \n Five Veo model variants available, ranging from Veo 2 to Veo 3.1, with trade-offs between speed and quality \n Supports cinematic, product, nature, action, and urban scene generation with detailed prompt control over camera movements, lighting, and timing \n Requires inference.sh CLI ( infsh ) for authentication and app execution \n Includes sample workflow for generating input templates and iterating on prompts \n